review

Code review with semantic diffs, expert routing, and auto-TaskCreate. Triggers on: code review, review changes, check code, review PR, security audit.

Install with Tessl CLI

npx tessl i github:NeverSight/skills_feed --skill review

What are skills?

Review — 87%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

93%

37%

API Endpoint Review

Review output format and severity system

Criteria

Without context

With context

CRITICAL severity used

100%

WARNING severity used

50%

100%

SUGGESTION severity used

50%

100%

PRAISE section present

100%

Verdict present

70%

100%

Summary table

50%

100%

File:line references

100%

Diff block fix

100%

Named review sections

87%

100%

Files Reviewed table

37%

100%

Tool availability check

Staged diff used

100%

Without context: $0.3514 · 1m 39s · 18 turns · 23 in / 5,661 out tokens

With context: $0.6377 · 2m 23s · 27 turns · 31 in / 8,350 out tokens

93%

15%

Full-Stack Feature Review

Expert routing and project standards loading

Criteria

Without context

With context

TypeScript expert routed

100%

Python expert routed

100%

SQL expert routed

100%

AGENTS.md loaded

100%

Linting config loaded

100%

delta tool checked

100%

difft tool checked

100%

File categorisation

87%

100%

Parallel dispatch noted

Review covers all file types

100%

Project convention applied

100%

Staged diff used

100%

Without context: $0.3343 · 1m 47s · 19 turns · 21 in / 6,387 out tokens

With context: $0.6278 · 2m 33s · 28 turns · 62 in / 8,608 out tokens

70%

13%

Payment Service Security Audit

CRITICAL task creation and dependency linking

Criteria

Without context

With context

Task per CRITICAL issue

100%

subject field format

activeForm field present

description field present

100%

blockedBy linking used

33%

66%

CRITICAL review findings

100%

Webhook signature noted

100%

Line references in review

100%

Diff block fixes

100%

TaskUpdate completed pattern

Ready to commit verdict

100%

Without context: $0.4295 · 2m 43s · 18 turns · 21 in / 8,617 out tokens

With context: $0.9970 · 3m 57s · 38 turns · 287 in / 12,339 out tokens

Evaluated: about 13 hours ago
Agent: Claude Code

Table of Contents

API Endpoint Review Full-Stack Feature Review Payment Service Security Audit

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.